基于积分图像的快速二维Otsu阈值法

Fast Two-dimensional Otsu's Thresholding Method Based on Integral Image

传统的二维Otsu法采用灰度级-平均灰度级二维直方图,针对传统二维直方图区域划分存在的不足,基于灰度级-梯度二维直方图,提出了一种引入积分图像的快速二维Otsu法,利用积分图像降低搜索二维直方图最佳阈值的计算复杂度,从而减少了计算量。实验结果表明,该方法具有良好的分割效果,大大地提高了计算速度,是一种快速有效且实时性好的阈值分割算法。

The traditional two-dimensional Otsu's threshold method uses gray level-average gray level two-dimensional histogram,but there are obvious deficiencies in the regional division of the traditional histogram.In this paper,an improved fast two-dimensional Otsu's threshold method with integral image based on gray level-gradient two-dimensional histogram was proposed.Using integral image to reduce the computational complexity in searching the best threshold value of two-dimensional histogram,thereby reducing the calculation amount.The results show that the method has a good segmentation effect which greatly and significantly increases the computing speed.Therefore,it is a fast and effective image segmentation method with a good real-time quality.